Creation of Man began from droplet of liquid and the end of Man will surely be De*th! Be Humble and spread LOVE โค๏ธ ๐
The internet is filled with endless opportunities
STOP WASTING HOURS TRYING TO FIGURE OUT WHAT TO LEARN IN AI.
I put together one practical roadmap with videos, GitHub repos, guides, books, research papers, and courses.
VIDEOS:
1. LLM Introduction โ youtube.com/watch?v=zjkBMFโฆ
2. LLMs from Scratch โ youtube.com/watch?v=9vM4p9โฆ
3. Agentic AI Overview (Stanford) โ youtube.com/watch?v=kJLiOGโฆ
4. Building & Evaluating Agents โ youtube.com/watch?v=d5EltXโฆ
5. Building Effective Agents โ youtube.com/watch?v=D7_ipDโฆ
6. Building Agents with MCP โ youtube.com/watch?v=kQmXtrโฆ
7. Building an Agent from Scratch โ youtube.com/watch?v=xzXdLRโฆ
8. Philo Agents โ youtube.com/playlist?list=โฆ
GITHUB REPOS:
1. GenAI Agents โ github.com/nirdiamant/Genโฆ
2. Microsoft AI Agents for Beginners โ github.com/microsoft/ai-aโฆ
3. Prompt Engineering Guide โ github.com/dair-ai/Promptโฆ
4. Hands-On Large Language Models โ github.com/HandsOnLLM/Hanโฆ
5. GenAI Agents โ github.com/NirDiamant/Genโฆ
6. Made with ML โ github.com/GokuMohandas/Mโฆ
7. Hands-On AI Engineering โ github.com/Sumanth077/Hanโฆ
8. Awesome Generative AI Guide โ github.com/aishwaryanr/awโฆ
9. Designing Machine Learning Systems โ github.com/chiphuyen/dmlsโฆ
10. Machine Learning for Beginners โ github.com/microsoft/ML-Fโฆ
11. LLM Course โ github.com/mlabonne/llm-cโฆ
GUIDES:
1. Google's Agent Whitepaper โ kaggle.com/whitepaper-ageโฆ
2. Google's Agent Companion โ kaggle.com/whitepaper-ageโฆ
3. Building Effective Agents by Anthropic โ anthropic.com/engineering/buโฆ
4. Claude Code Agentic Coding Practices โ code.claude.com/docs/en/bestโฆโฆ
5. OpenAI's Practical Guide to Building Agents โ cdn.openai.com/business-guidโฆโฆ
BOOKS:
1. Understanding Deep Learning โ udlbook.github.io/udlbook/
2. Building an LLM from Scratch โ manning.com/books/build-a-โฆ
3. The LLM Engineering Handbook โ oreilly.com/library/view/lโฆ
4. AI Agents: The Definitive Guide โ oreilly.com/library/view/aโฆ
5. Building Applications with AI Agents โ oreilly.com/library/view/bโฆ
6. AI Agents with MCP โ oreilly.com/library/view/aโฆ
7. AI Engineering โ oreilly.com/library/view/aโฆ
RESEARCH PAPERS:
1. ReAct โ arxiv.org/abs/2210.03629
2. Generative Agents โ arxiv.org/abs/2304.03442
3. Toolformer โ proceedings.neurips.cc/paperโฆโฆ
4. Chain-of-Thought Prompting โ arxiv.org/pdf/2201.11903
COURSES:
1. Hugging Face Agent Course โ huggingface.co/learn/agents-โฆโฆ
2. MCP with Anthropic โ deeplearning.ai/courses/mcp-โฆโฆ
3. Building Vector Databases with Pinecone โ deeplearning.ai/courses/builโฆโฆ
4. Vector Databases: Embeddings to Apps โ deeplearning.ai/courses/vectโฆโฆ
5. Agent Memory โ deeplearning.ai/courses/llmsโฆโฆ
No endless searching.
No information overload.
Just resources you can actually use. ๐
Your future AI skill set will come from consistent building, experimenting, and learning.
Repost so someone else can find this roadmap, and pls consider following.
follow
@trreo7 for more content around AI, Beauty, and businesses.
7
This is interesting
This is f*cking insane. Andrej Karpathy spent 70 minutes showing how top AI users actually work with LLMs
And most people are overcomplicating it
Prompts โ Context โ Tools โ Workflows โ How the Top 1% Work
He co-founded OpenAI and led AI at Tesla. This is the hour he spent on how it's really done
Worth more than any $2,000 AI course
Bookmark and watch it today
Then read how to set up your own: Harness, Loops, Graphs โ
1
Interesting for mercor applicants
if you truly want to be hired on mercor
let me give you some advice.
take this weekend and complete these two courses on mercor
once done, pick up your cv and update your professional certificate
from monday, stop applying to skill based roles, instead focus on generalist roles
there about 5 generalist roles opened and i shared them in my previous post, would drop link in comments
with these courses done, your skills and certificate updated on your cv, you stand a better chance of getting hiredโฆ
50
Masterpiece
AI ENGINEER ROADMAP 2026
โ Programming Fundamentals
- Python
- Data structures and algorithms
- Object-oriented programming
- Functional programming
- Type hints
- Async programming
- Git and GitHub
- Linux fundamentals
- SQL
โก Mathematics for AI
- Linear algebra
- Calculus
- Probability
- Statistics
- Discrete mathematics
- Optimization
- Gradient descent
- Matrix operations
- Numerical computing
โข Data Engineering Fundamentals
- Data collection
- Data cleaning
- Data preprocessing
- Feature engineering
- Exploratory data analysis
- Data transformation
- SQL and NoSQL databases
- Data pipelines
- Apache Spark
- Data versioning
โฃ Machine Learning
- Supervised learning
- Unsupervised learning
- Reinforcement learning
- Regression
- Classification
- Clustering
- Decision trees
- Random forests
- Support Vector Machines
- XGBoost
- Model evaluation
- Cross-validation
- Hyperparameter tuning
โค Deep Learning
- Neural networks
- Perceptrons
- Backpropagation
- Activation functions
- Loss functions
- Optimizers
- CNNs
- RNNs
- LSTMs
- Transformers
- Transfer learning
- PyTorch
- TensorFlow
โฅ Natural Language Processing (NLP)
- Text preprocessing
- Tokenization
- Word embeddings
- TF-IDF
- Word2Vec
- Named Entity Recognition
- Sentiment analysis
- Language modeling
- Attention mechanisms
- Transformer architectures
- Hugging Face
โฆ Large Language Models (LLMs)
- LLM fundamentals
- Transformer architecture
- Tokenization
- Prompt engineering
- Context windows
- Embeddings
- Fine-tuning
- LoRA and QLoRA
- Quantization
- Model evaluation
- Open-source LLMs
- Model inference
- LLM APIs
โง Retrieval-Augmented Generation (RAG)
- RAG architecture
- Document ingestion
- Text chunking
- Embedding models
- Vector databases
- Semantic search
- Hybrid search
- Reranking
- Query transformation
- Context retrieval
- Advanced RAG
- RAG evaluation
โจ AI Agents & Agentic Systems
- AI agent fundamentals
- Tool calling
- Function calling
- Planning and reasoning
- Memory management
- Multi-agent systems
- Agent orchestration
- Workflow automation
- MCP
- LangGraph
- CrewAI
- AutoGen
- Agent evaluation
- Human-in-the-loop
โฉ AI Frameworks & Ecosystem
- PyTorch
- TensorFlow
- Hugging Face
- LangChain
- LangGraph
- LlamaIndex
- OpenAI API
- Anthropic API
- Google Gemini API
- Ollama
- vLLM
- MLflow
โช AI System Design
- AI architecture
- Model serving
- Inference optimization
- Distributed computing
- GPU acceleration
- Caching
- Load balancing
- Model routing
- Streaming responses
- Microservices
- Event-driven architecture
- Scalable AI pipelines
โซ MLOps & LLMOps
- Experiment tracking
- Model versioning
- Data versioning
- Model deployment
- CI/CD for ML
- Model monitoring
- Data drift detection
- Model drift detection
- Automated retraining
- LLM observability
- Evaluation pipelines
- MLflow
- Kubeflow
- Weights & Biases
โฌ AI Infrastructure & Cloud
- Linux
- Docker
- Kubernetes
- NVIDIA CUDA
- GPU computing
- AWS
- Google Cloud
- Microsoft Azure
- Serverless AI
- Vector databases
- Redis
- PostgreSQL
- Cloud deployment
โญ AI Security & Responsible AI
- AI safety
- Responsible AI
- Bias and fairness
- Explainable AI
- Data privacy
- Prompt injection
- Jailbreak prevention
- Data leakage prevention
- Adversarial attacks
- Guardrails
- AI governance
- Model security
โฎ Build Real-World AI Projects
- AI-powered chatbot
- Document Q&A system
- RAG search engine
- AI research assistant
- AI coding assistant
- Multi-agent research system
- Recommendation engine
- Image classification system
- Speech-to-text application
- AI customer support agent
- AI SaaS platform
- Production-ready AI workflow automation
โฏ AI Engineer Career Specializations
- Machine Learning Engineer
- Deep Learning Engineer
- LLM Engineer
- AI Infrastructure Engineer
- Generative AI Engineer
- RAG Engineer
- AI Agent Engineer
- MLOps Engineer
- Applied AI Engineer
- AI Research Engineer
Save this roadmap. Build projects. Become an AI Engineer.
This is masterpiece
THIS IS A GOLDMINE FOR ANYONE WHO WANTS TO BECOME AN AI ENGINEER AND WORK AT ANTHROPIC
So I collected 12 FREE resources and organized them into a 12-week build plan
Python โ neural networks โ LLMs โ RAG โ agents โ production
Each step gives you something to build, test, and explain
01 Python foundations โ Harvard CS50P
Functions, testing, debugging, and the coding skills everything else depends on.
cs50.harvard.edu/python/
02 Practical deep learning โ fast.ai
Train useful models and turn them into applications.
course.fast.ai/
03 Neural networks from scratch โ Andrej Karpathy
Build neural networks, understand backpropagation, and work toward GPT.
github.com/karpathy/nn-zero-โฆ
04 PyTorch fundamentals
Tensors, datasets, automatic differentiation, and training loops.
docs.pytorch.org/tutorials/bโฆ
05 LLMs and fine-tuning โ Hugging Face
Understand Transformers, tokenization, and adapting pretrained models.
huggingface.co/learn/llm-couโฆ
06 Building LLM applications โ Full Stack Deep Learning
Connect language models to useful products. Study prompting, retrieval, and LLMOps.
fullstackdeeplearning.com/llโฆ
07 RAG โ DataTalks.Club
Build an assistant that answers questions using your documents.
github.com/DataTalksClub/llmโฆ
08 AI agents โ Hugging Face
Build systems that use tools and carry out tasks through agent workflows.
huggingface.co/learn/agents-โฆ
09 Agent architecture โ Anthropic
Learn routing, parallelization, orchestration, and evaluator loops.
anthropic.com/engineering/buโฆ
10 MCP โ Hugging Face
Connect AI applications to external tools and data sources.
huggingface.co/learn/mcp-couโฆ
11 Production engineering โ Made With ML
Evaluation, testing, serving, CI/CD, and monitoring.
madewithml.com/
12 MLOps โ DataTalks.Club
Experiment tracking, orchestration, deployment, and maintaining models.
github.com/DataTalksClub/mloโฆ
Follow one step per week. Use selected lessons to finish a project milestone before moving on
Your target portfolio: a model-training project, a RAG assistant with citations, and a tool-using agent with evaluations and a deployment workflow
Plan for 10โ15 hours a week with basic Python knowledge. Completing every course takes longer. Learning materials are free; APIs and compute may cost extra
Pick the first resource you need. Build something worth putting your name on
Save this โ
2
The best industrialist after Dangote in Nigeria
Abdul Samad Rabiu, founder of BUA Group, on how Dangote stopped his Porthacourt Sugar Refinery from operating
He says Dangote went to the government and came up with the idea.
That anyone building sugar refinery in Nigeria must have a sugar plantation, must be seen to be doing a backward integration program and must not operate more than one refinery in Nigeria.
And the government would give allocation to import raw sugar.
He also says they were halfway into completing the project but they had to abandon it.
24
Comment with your course, and I may help you find a full funding scholarship that matches your field.
12
๐จ GET PAID $600+ JUST BY TYPING AND CHATTING!
Worldwide Remote
$1240/month
No VPN needed. No experience needed.
Must be Ready to work Flexibly
1
25
Anyone currently on ground in AAU Ekpoma who can assist with academic consults pls. Iโd gladly pay for better than travelling down
2
23

















